veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

the-crypt-keeper

#
# this is adapted from https://github.com/facebookresearch/llama/blob/main/llama/generation.py#L213
# the tokenizer is replaced with ord() to make it easier to see whats actually happening

from typing_extensions import TypedDict, Literal
from typing import List, Optional

Role = Literal["system", "user", "assistant"]

class Message(TypedDict):

dsevero

espoirMur

I am no longer abe to monitor this post , I have decided to move everything to my personal blog for better monitoring.

Please click here to access the full post

AlexeyGy

import baker
import json
import os
from cytoolz import merge, join, groupby
from cytoolz.compatibility import iteritems
from cytoolz.curried import update_in
from itertools import starmap
from collections import deque
from lxml import etree, objectify
from scipy.io import savemat

nealrs

"""
this code is not mine! i shamelessly copied it from http://stackoverflow.com/questions/19790188/expanding-english-language-contractions-in-python
all credits go to alko and arturomp @ stack overflow.

basically, it's a big find/replace.
"""

import re
cList = {
  "ain't": "am not",

henrik

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name: